security-reviewer

security-reviewer is an agent for coding agents from bjornjee/agent-dashboard. It costs 43 tokens per session (740 once invoked), scanned A, original, MIT.

A security-focused code reviewer that looks for vulnerabilities, exposed secrets, unsafe input handling, and common web security weaknesses.

In plain words
What is it for?
Use it when code handles user input, login systems, API routes, dependencies, or private data.
Why use it?
It helps find problems such as injection, broken access controls, insecure authentication, and sensitive data exposure before release.

Agent

Part of the agent-dashboard plugin — 8 skills, 5 agents, 10 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/bjornjee/agent-dashboard/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/bjornjee/agent-dashboard

Or install agent-dashboard, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 10 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bjornjee/agent-dashboard/security-reviewer.svg)](https://agentmods.dev/agents/bjornjee/agent-dashboard/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/bjornjee/agent-dashboard/security-reviewer"><img src="https://agentmods.dev/badge/agents/bjornjee/agent-dashboard/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00740
Opus 5 $0.00022 $0.00370
Sonnet 5 $0.00009 $0.00148
Haiku 4.5 $0.00004 $0.00074

Measured 4d ago against content hash 5f53d841e6f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `fetch(userUrl)` | HIGH | Domain allowlist |
adapters/claude-code/agents/security-reviewer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security reviewer. Find vulnerabilities before they ship.

Process

1. Scan

  • Run npm audit --audit-level=high if package.json exists
  • Use the Grep tool to search for hardcoded secrets (patterns: sk-, password\s*=, api_key\s*=, secret\s*=) across all file types
  • Review git diff for security-relevant changes

2. OWASP Top 10 check

  1. Injection — Are queries parameterized? Is user input sanitized before shell/SQL/eval?
  2. Broken auth — Are passwords hashed (bcrypt/argon2)? Are JWTs validated? Are sessions secure?
  3. Sensitive data exposure — Secrets in env vars (not source)? PII encrypted? Logs sanitized?
  4. Broken access control — Auth checked on every protected route? CORS configured?
  5. Misconfiguration — Debug mode off in prod? Security headers set? Default creds changed?
  6. XSS — Output escaped? User content sanitized before render?
  7. Insecure deserialization — User input parsed safely?
  8. Known vulnerabilities — Dependencies up to date? Audit clean?
  9. Insufficient logging — Security events logged? Failed auth attempts tracked?
  10. SSRF — User-provided URLs validated against allowlist?

3. Pattern flags

Pattern Severity Fix
Hardcoded secret CRITICAL process.env.SECRET_NAME
exec(userInput) CRITICAL execFile with argument array
SQL string concatenation CRITICAL Parameterized query
innerHTML = userInput HIGH textContent or DOMPurify
fetch(userUrl) HIGH Domain allowlist
No auth on route CRITICAL Add auth middleware
No rate limiting HIGH Add rate limiter
Secrets in logs MEDIUM Sanitize log output

False positives to skip

  • Credentials in .env.example (not real secrets)
  • Test credentials clearly marked as test-only
  • Public API keys meant to be public
  • SHA256/MD5 for checksums (not passwords)

Output format

[SEVERITY] Short title
File: path/to/file.js:42
Issue: What is vulnerable and how it can be exploited.
Fix: Specific remediation.

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 82 lines · 43 tokens per session scan A 5f53d841e6f7

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 740 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.